Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/examples/demo19.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,13 @@
 ---
-title: Stable Depth2image V2
-emoji: 🐠
-colorFrom: purple
-colorTo: purple
+title: Stable Depth2Image V2
+emoji: 🌖
+colorFrom: green
+colorTo: indigo
 sdk: gradio
-sdk_version: 4.39.0
+sdk_version: 4.36.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,128 @@
+import gradio as gr
+import matplotlib
+import numpy as np
+import random
+import os
+from PIL import Image
+import spaces
+import torch
+from gradio_imageslider import ImageSlider
+from transformers import pipeline
+from diffusers import StableDiffusionDepth2ImgPipeline
+
+
+model_id_depth = "depth-anything/Depth-Anything-V2-Large-hf"
+if torch.cuda.is_available():
+    pipe_depth = pipeline(task="depth-estimation", model=model_id_depth, device="cuda")
+else:
+    pipe_depth = pipeline(task="depth-estimation", model=model_id_depth)
+model_id_depth2image = "stabilityai/stable-diffusion-2-depth"
+if torch.cuda.is_available():
+    pipe_depth2image = StableDiffusionDepth2ImgPipeline.from_pretrained(model_id_depth2image, torch_dtype=torch.float16).to("cuda")
+else:
+    pipe_depth2image = StableDiffusionDepth2ImgPipeline.from_pretrained(model_id_depth2image)
+max_seed = np.iinfo(np.int32).max
+max_image_size = 1344
+example_files = [os.path.join('assets/examples', filename) for filename in sorted(os.listdir('assets/examples'))]
+
+
+@spaces.GPU
+def infer(
+        init_image,
+        prompt,
+        negative_prompt,
+        seed,
+        randomize_seed,
+        width,
+        height,
+        guidance_scale,
+        num_inference_steps):
+    if randomize_seed:
+        seed = random.randint(0, max_seed)
+    init_image = Image.fromarray(np.uint8(init_image))
+    # generate depth
+    predicted_depth = pipe_depth(init_image)["predicted_depth"]
+    # generate image
+    image = pipe_depth2image(
+        prompt=prompt,
+        image=init_image,
+        depth_map=predicted_depth,
+        negative_prompt=negative_prompt,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        height=height,
+        width=width,
+        generator=torch.Generator().manual_seed(seed)
+    ).images[0]
+    return image, seed
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Demo [Depth2Image](https://huggingface.co/stabilityai/stable-diffusion-2-depth) with depth map estimated by [Depth Anything V2](https://huggingface.co/depth-anything/Depth-Anything-V2-Large-hf).")
+    prompt = gr.Text(
+        label="Prompt",
+        show_label=False,
+        max_lines=1,
+        placeholder="Enter your prompt",
+        container=False,
+    )
+    with gr.Row():
+        init_image = gr.Image(label="Input Image", type='numpy')
+        result = gr.Image(label="Result", show_label=False)
+    run_button = gr.Button("Run", scale=0)
+    with gr.Accordion("Advanced Settings", open=False):
+        negative_prompt = gr.Text(
+            label="Negative Prompt",
+            max_lines=1,
+            placeholder="Enter a negative prompt",
+        )
+        seed = gr.Slider(
+            label="Seed",
+            minimum=0,
+            maximum=max_seed,
+            step=1,
+            value=0,
+        )
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Row():
+            width = gr.Slider(
+                label="Width",
+                minimum=256,
+                maximum=max_image_size,
+                step=64,
+                value=1024,
+            )
+            height = gr.Slider(
+                label="Height",
+                minimum=256,
+                maximum=max_image_size,
+                step=64,
+                value=1024,
+            )
+        with gr.Row():
+            guidance_scale = gr.Slider(
+                label="Guidance scale",
+                minimum=0.0,
+                maximum=10.0,
+                step=0.1,
+                value=7.5,
+            )
+            num_inference_steps = gr.Slider(
+                label="Number of inference steps",
+                minimum=1,
+                maximum=50,
+                step=1,
+                value=5,
+            )
+    gr.on(
+        triggers=[run_button.click, prompt.submit, negative_prompt.submit],
+        fn=infer,
+        inputs=[init_image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, seed]
+    )
+    examples = gr.Examples(
+        examples=example_files, inputs=[init_image], outputs=[depth_image_slider, gray_depth_file], fn=on_submit
+    )
+
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,7 @@
+git+https://github.com/huggingface/diffusers.git
+transformers
+accelerate
+sentencepiece
+gradio==4.36.0
+torch
+matplotlib